CN109917457A - A kind of pick-up method and equipment of seismic first breaks point - Google Patents
A kind of pick-up method and equipment of seismic first breaks point Download PDFInfo
- Publication number
- CN109917457A CN109917457A CN201910283946.6A CN201910283946A CN109917457A CN 109917457 A CN109917457 A CN 109917457A CN 201910283946 A CN201910283946 A CN 201910283946A CN 109917457 A CN109917457 A CN 109917457A
- Authority
- CN
- China
- Prior art keywords
- data
- training set
- test set
- seismic wave
- window
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012360 testing method Methods 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 42
- 230000000306 recurrent effect Effects 0.000 claims abstract description 23
- 238000003062 neural network model Methods 0.000 claims abstract description 22
- 230000001537 neural effect Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000003860 storage Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 16
- 238000005070 sampling Methods 0.000 claims description 8
- 241001269238 Data Species 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 210000004218 nerve net Anatomy 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 239000010410 layer Substances 0.000 description 16
- 230000006870 function Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000003475 lamination Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
Abstract
The invention discloses a kind of pick-up methods of seismic first breaks point, are several data windows by per pass Seismic wave processing comprising steps of carrying out default processing respectively to multiple tracks seismic wave；The first training set and the first test set are constructed using the data window of multiple tracks seismic wave, and there are the data windows of Onset point to construct the second training set and the second test set using all；Building classification and recurrent neural network model；It is utilized respectively the first training set and the first test set and the second training set and the second test set Classification Neural and recurrent neural network model are trained and are tested；The seismic wave to be picked up by default processing is made inferences using trained Classification Neural and recurrent neural network model, first obtains the data window there are Onset point, then there are the data window first break picking points of Onset point.Method disclosed by the invention can be realized the accurate prediction of first arrival time in data window by the combination using classification and recurrent neural networks.
Description
Technical field
The present invention relates to seismic survey fields, and in particular to a kind of pick-up method and equipment of seismic first breaks point.
Background technique
The automatic first break pickup of seismic wave is always that one of seismic survey work under the conditions of complicated landform and surface layer is important
Problem is the pretreated key business link of seismic data.The research and application of first break pickup technology have nearly 40 years history, perhaps
More scholars propose a variety of methods and the relevant technologies application, and first break pickup, which mostly uses greatly, at present is manually marked with machine cooperation
Note, picks up efficiency and pickup cost still has greater room for improvement, simultaneously because subjective factor influences, different majors personnel's first arrival
It picks up result to be not quite similar, therefore it is particularly important for first break pickup to find efficient and accurate method.
The target of first break pickup is the time found seismic wave and initially reach geophone station, and researcher proposes a variety of sides
Method, if instantaneous strength is than method, neural network algorithm, digital image processing method, wherein STA/LTA is a kind of classical based on earthquake
When window feature processing method, have many advantages, such as that high degree of automation, calculating speed are fast；Neural network structure is simple, is easy to real
It is existing, therefore very early just by application and first break pickup field, but the algorithm is slow in the presence of convergence, easily sinks into local extremum, network knot
Structure is difficult to the problems such as determining.And method mentioned above is single track pick-up method, the correlation that only considered single seismic channel is special
The similitude of sign, the seismic signal not recorded using multiple tracks cross-correlation method by the different stations completes pickup work, can not have
There is anti-noise and picks up the features such as precision is high.
In general, the existing technology of first break pickup has the disadvantage that
1) for complex area low SNR data, traditional first break pickup technique picks effect is undesirable；
2) there is corresponding advantage and defect in different technologies, need to select suitable first arrival to pick up according to actual seismic information attribute
Take method；
3) first break pickup method relies on the semi-automatic pickup technology of human-computer interaction at present.
Summary of the invention
In view of this, at least one aspect in order to overcome the above problem, the embodiment of the present invention propose a kind of seismic wave
The pick-up method of Onset point, comprising steps of
It carries out default processing respectively to multiple tracks seismic wave, is several data windows by per pass Seismic wave processing；
The first training set and the first test set are constructed using the data window of multiple tracks seismic wave, and there are first arrivals using all
The data window of point constructs the second training set and the second test set；
Construct Classification Neural model and recurrent neural network model；
The Classification Neural model is trained and is tested using first training set and the first test set, and
The recurrent neural network model is trained and is tested using second training set and the second test set；
The seismic wave to be picked up by default processing is made inferences using trained Classification Neural model, is obtained
There are the data windows of Onset point, and then using trained recurrent neural network model, there are the data windows of Onset point described
The Onset point is picked up in mouthful.
In some embodiments, default handle includes:
Seismic wave is sampled, to obtain multiple sampled datas, and then using described in the multiple sampled data composition
Several data windows.
In some embodiments, the default processing further include: before sampling, seismic wave is converted into metric vibration
Width data, and divided by amplitude data maximum absolute value value, to obtain the seismic wave that amplitude data range is [- 1,1].
In some embodiments, the first training set and the first test set are constructed into one using the data window of multiple tracks seismic wave
Step includes:
Using each data window as middle window, two adjacent data windows are respectively as upper and lower window, altogether
With one sample of composition, the first training set and the first test set are constructed after obtaining multiple samples, wherein if as middle window
Only one adjacent data window of data window carries out zero padding processing.
In some embodiments, the first training set and the first test set are constructed into one using the data window of multiple tracks seismic wave
Step includes:
It tags for the first training set and first test set, first training set and/or first test set
Label be that whether there is Onset point as the data window of middle window, Onset point if it exists, then label is 1, otherwise label
It is 0.
In some embodiments, there are the data windows of Onset point to construct the second training set and the second test set using all
Further comprise:
It tags for the second training set and second test set, second training set and/or second test set
Label be the corresponding first arrival time of the Onset point.
In some embodiments, the Classification Neural model is instructed using the first training set and the first test set
Practice and test, and recurrent neural network model is trained using the second training set and the second test set and test includes:
When testing trained Classification Neural model and/or recurrent neural network model, if test result
Required precision is not met, then continues to be trained the Classification Neural model and/or the recurrent neural network model,
Until test result meets required precision.
In some embodiments, the method also includes steps:
Using the more big gun single tracks of visualization model output pick up results, single-shot multiple tracks picks up result, single track picks up result and pre-
Survey at least one of error box traction substation.
Based on the same inventive concept, according to another aspect of the present invention, the embodiments of the present invention also provide a kind of meters
Calculate machine equipment, comprising:
At least one processor；And
Memory, the memory are stored with the computer program that can be run on the processor, and the processor is held
The step of pick-up method of any seismic first breaks point as described above is executed when row described program.
Based on the same inventive concept, according to another aspect of the present invention, the embodiments of the present invention also provide a kind of meters
Calculation machine readable storage medium storing program for executing, the computer-readable recording medium storage have computer program, and the computer program is processed
The step of pick-up method of any seismic first breaks point as described above is executed when device executes.
The present invention has following advantageous effects: per pass seismic data is divided by method disclosed by the invention first
Multiple data windows find the data window comprising Onset point using depth of assortment neural network model, recycle Recurrent networks
Structure realizes the accurate prediction of first arrival time in data window, can complete the accurate prediction to focus earthquake wave number evidence.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other embodiments are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of the pick-up method for seismic first breaks point that the embodiment of the present invention provides；
Fig. 2 is that the data window that the embodiment of the present invention provides constructs sample set structural schematic diagram；
More big gun single tracks that the pick-up method for the seismic first breaks point that Fig. 3 is provided using the embodiment of the present invention obtains pick up knot
Fruit；
The single-shot single track that the pick-up method for the seismic first breaks point that Fig. 4 is provided using the embodiment of the present invention obtains picks up knot
Fruit；
The consistent pickup result that the pick-up method for the seismic first breaks point that Fig. 5 is provided using the embodiment of the present invention obtains is shown
It is intended to；
The inconsistent pickup result that the pick-up method for the seismic first breaks point that Fig. 6 is provided using the embodiment of the present invention obtains
Schematic diagram；
The pickup result that the pick-up method for the seismic first breaks point that Fig. 7 is provided using the embodiment of the present invention obtains is accumulative to be missed
Difference cloth；
Fig. 8 is the structural schematic diagram for the computer equipment that the embodiment of the present invention provides；
Fig. 9 is the structural schematic diagram for the computer readable storage medium that the embodiment of the present invention provides.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
The embodiment of the present invention is further described in attached drawing.
It should be noted that all statements for using " first " and " second " are for differentiation two in the embodiment of the present invention
The non-equal entity of a same names or non-equal parameter, it is seen that " first " " second " only for the convenience of statement, does not answer
It is interpreted as the restriction to the embodiment of the present invention, subsequent embodiment no longer illustrates this one by one.
According to an aspect of the present invention, the embodiment of the present invention proposes a kind of pick-up method of seismic first breaks point, such as
May include step shown in Fig. 1:
It carries out default processing respectively to multiple tracks seismic wave, is several data windows by per pass Seismic wave processing.
In some embodiments, seismic data is all to store in binary form, such as SEG-Y data format.SEG-Y lattice
The concrete meaning of formula can be as shown in table 1, and it includes the important seismic datas such as big gun number, Taoist monastic name, sampling number, sampling period.
1 SEG-Y standard disk file format of table
In order to carry out the pickup of Onset point to seismic wave, data format conversion module can use first for binary system
Original seismic wave data conversion at metric seismic data, can will be after conversion in further preferred embodiment
Data visualize and be compared with earthquake analysis processing software SeiSee result, to confirm the correct of translated data
Property.
In some embodiments, after the conversion for carrying out data format to original multiple tracks seismic wave, availablely
Seismic wave data save as amplitude data, then utilize data preprocessing module to each road seismic waveform amplitude data divided by it
Per pass amplitude data maximum absolute value value obtains the seismic wave that amplitude data range is [- 1,1] after converting.
In some embodiments, after obtaining the seismic wave that amplitude data range is [- 1,1], it can be carried out at sampling
Reason, the period of sampling can be 4ms, after being sampled in this way to per pass seismic wave, available 626 sampled datas, such as table 2
Shown, table 2 is the multiple tracks seismic data sample instantiation generated by data preprocessing module, and Feature 1-626 indicates inspection
The amplitude data that wave point periodic sampling arrives, label indicate the first arrival time of single-channel seismic waveform.Certainly, in other embodiments,
Other sampling periods can also be used to obtain the use data of different number.
2 multiple tracks seismic data sample instantiation of table
| Feature1 | Feature2 | Feature3 | … | Feature625 | Feature626 | label |
| 0.304 | 0.574 | -0.368 | … | 0.173 | 0.346 | 30 |
| 0.453 | -0.658 | 0.234 | … | 0.763 | -0.547 | 36 |
| … | … | … | … | … | … | … |
| 0.546 | -0.353 | 0.235 | … | -0.532 | 0.453 | 80 |
In some embodiments, it after being sampled to per pass seismic data, can be adopted according to the multiple of per pass seismic wave
Sample data constitute data window.
For example, single-channel seismic wave number in table 2 can be divided into 21 data windows, every number according to Feature 1-626
According to including 30 sampled datas in window, wherein the 21st data window includes 26 sampled datas, to its remaining 4 hits
According to zero padding operation can be carried out.
The pick-up method of seismic first breaks point of the invention can with comprising steps of
The first training set and the first test set are constructed using the data window of multiple tracks seismic wave, and there are first arrivals using all
The data window of point constructs the second training set and the second test set.
In some embodiments, the first training set and the first test set are constructed into one using the data window of multiple tracks seismic wave
Step includes:
Using each data window as middle window, two adjacent data windows are respectively as upper and lower window, altogether
With one sample of composition, the first training set and the first test set are constructed after obtaining multiple samples, wherein if as middle window
Only one adjacent data window of data window carries out zero padding processing.
Specifically, as shown in Fig. 2, each road seismic wave sample can be moved to right a data window and is placed in
Side, is moved to left that a data window is placed below, Sample indicate by 3 data group of windows at a training sample, i.e.,
First Sample is then made of first data window and second data window and zero, and second Sample is then by the
One data window, the second data window and third data group of windows at, and so on, per pass seismic wave available 21
Sample.And the corresponding label of each Sample is that whether there is Onset point as the data window of middle window, if it exists then
This Sample label is set as 1, otherwise label is 0.
In some embodiments, the label of second training set and/or second test set can be the first arrival
The corresponding first arrival time of point.
In some embodiments, training dataset can account for the 80% of total number of samples, remaining 20% be used as test data set.
The pick-up method of seismic first breaks point of the invention can be comprising steps of constructing Classification Neural model and returning
Return neural network model.
In some embodiments, Classification Neural model may include:
First convolutional layer may include the convolution kernel of 32 3*1；
Second convolutional layer may include the convolution kernel of 64 3*1；
Third convolutional layer may include the convolution kernel of 64 2*1；
Volume Four lamination may include the convolution kernel of 64 3*1；
5th convolutional layer may include the convolution kernel of 64 2*1；
First full articulamentum, can have 256 channels；
Second full articulamentum, can have 256 channels；
Output layer.
The data for being input to Classification Neural model can successively pass through the first convolutional layer, the second convolutional layer, third volume
After lamination, Volume Four lamination, the 5th convolutional layer, the first full articulamentum and the second full articulamentum processing, exported by output layer.
In some embodiments, recurrent neural network model may include:
First convolutional layer may include the convolution kernel of 150 3*1；
Second convolutional layer may include the convolution kernel of 100 3*1；
Third convolutional layer may include the convolution kernel of 80 3*1；
Volume Four lamination may include the convolution kernel of 160 3*1；
First full articulamentum, can have 100 channels；
Second full articulamentum, can have 100 channels；
Output layer.
The data for being input to recurrent neural network model can successively pass through the first convolutional layer, the second convolutional layer, third volume
After lamination, Volume Four lamination, the first full articulamentum and the second full articulamentum processing, exported by output layer.
The pick-up method of seismic first breaks point of the invention can with comprising steps of
The Classification Neural model is trained and is tested using first training set and the first test set, benefit
The recurrent neural network model is trained and is tested with second training set and the second test set.
In some embodiments, after being trained using the first training set to Classification Neural model, first is being utilized
There are the general of Onset point for the corresponding each data window of per pass seismic data in available test set when test set is tested
Rate, value range can be [0,1], and the bigger expression of probability value more there may be Onset point.If obtained test result is discontented
Sufficient required precision then continues to train Classification Neural model, until test result meets required precision.
In some embodiments, after being trained using the second training set to recurrent neural network model, second is being utilized
First arrival in the corresponding data window there are Onset point of per pass seismic data in available test set when test set is tested
The correct time of point.If obtained test result is unsatisfactory for required precision, continue to train recurrent neural network model, until surveying
Test result meets required precision.
The pick-up method of seismic first breaks point of the invention can with comprising steps of
The seismic wave to be picked up by default processing is made inferences using trained Classification Neural model, is obtained
There are the data windows of Onset point, and then using trained recurrent neural network model, there are the data windows of Onset point described
The Onset point is picked up in mouthful.
In some embodiments, the pick-up method of seismic first breaks point can also include step, defeated using visualization model
More big gun single tracks pick up result out, single-shot multiple tracks picks up result, single track picks up result and prediction error box traction substation.
More big gun single tracks are exported specifically, can use result visualization module and be based on Python third party library matplotlib
It picks up scatter plot, single-shot multiple tracks pickup scatter plot, single track and picks up the statistic analysis results such as result figure, box traction substation, to facilitate user
Various dimensions, which are checked, picks up result situation.
For example, as shown in figure 3, it illustrates more big gun single tracks pick up scatter plot, as can be seen from the figure predict Onset point and
Practical Onset point essentially coincides.
For example, as shown in figure 4, it illustrates single-shot multiple tracks pick up scatter plot, as can be seen from the figure predict Onset point and
Practical Onset point essentially coincides.
For example, as shown in figure 5, picking up result schematic diagram it illustrates consistent, as can be seen from the figure first arrival is predicted in representative
The straight line of point is overlapped with the straight line for representing practical Onset point.
For example, as shown in fig. 6, as can be seen from the figure representing prediction just it illustrates inconsistent pickup result schematic diagram
Straight line to point is not overlapped with the straight line for representing practical Onset point.
For example, as shown in fig. 7, it illustrates pickup result cumulative errors of the invention distribution, as can be seen from the figure generation
The time of table prediction Onset point subtracts the straight line that the time of practical Onset point is 0 and is apparently higher than other straight lines, illustrates that the present invention mentions
The method of confession can accurately predict Onset point.
Based on the same inventive concept, according to another aspect of the present invention, as shown in figure 8, the embodiment of the present invention also mentions
Supply a kind of computer equipment 501, comprising:
At least one processor 520；And
Memory 510, memory 510 are stored with the computer program 511 that can be run on a processor, and processor 520 is held
The step of pick-up method of any seismic first breaks point as above is executed when line program.
Based on the same inventive concept, according to another aspect of the present invention, as shown in figure 9, the embodiment of the present invention also mentions
A kind of computer readable storage medium 601 is supplied, computer readable storage medium 601 is stored with computer program 610, computer
Program 610 executes the step of pick-up method of seismic first breaks point as above when being executed by processor.
Finally, it should be noted that those of ordinary skill in the art will appreciate that realizing the whole in above-described embodiment method
Or part process, related hardware can be instructed to complete by computer program, program to can be stored in one computer-readable
It takes in storage medium, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium
It can be magnetic disk, CD, read-only memory (ROM) or random access memory (RAM) etc..The implementation of above-mentioned computer program
Example, can achieve the identical or similar effect of corresponding aforementioned any means embodiment.
In addition, typically, device disclosed by the embodiments of the present invention, equipment etc. can be various electric terminal equipments, such as hand
Machine, personal digital assistant (PDA), tablet computer (PAD), smart television etc., are also possible to large-scale terminal device, such as server
Deng, therefore protection scope disclosed by the embodiments of the present invention should not limit as certain certain types of device, equipment.The present invention is implemented
Client disclosed in example, which can be, is applied to any one of the above electricity with the combining form of electronic hardware, computer software or both
In sub- terminal device.
In addition, disclosed method is also implemented as the computer program executed by CPU according to embodiments of the present invention, it should
Computer program may be stored in a computer readable storage medium.When the computer program is executed by CPU, the present invention is executed
The above-mentioned function of being limited in method disclosed in embodiment.
In addition, above method step and system unit also can use controller and for storing so that controller is real
The computer readable storage medium of the computer program of existing above-mentioned steps or Elementary Function is realized.
In addition, it should be appreciated that the computer readable storage medium (for example, memory) of this paper can be volatibility and deposit
Reservoir or nonvolatile memory, or may include both volatile memory and nonvolatile memory.As an example and
Unrestricted, nonvolatile memory may include read-only memory (ROM), programming ROM (PROM), electrically programmable ROM
(EPROM), electrically erasable programmable ROM (EEPROM) or flash memory.Volatile memory may include that arbitrary access is deposited
Reservoir (RAM), the RAM can serve as external cache.As an example and not restrictive, RAM can be with a variety of
Form obtains, such as synchronous random access memory (DRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate SDRAM (DDR
SDRAM), enhance SDRAM (ESDRAM), synchronization link DRAM (SLDRAM) and directly Rambus RAM (DRRAM).Institute is public
The storage equipment for the aspect opened is intended to the memory of including but not limited to these and other suitable type.
Those skilled in the art will also understand is that, various illustrative logical blocks, mould in conjunction with described in disclosure herein
Block, circuit and algorithm steps may be implemented as the combination of electronic hardware, computer software or both.It is hard in order to clearly demonstrate
This interchangeability of part and software, with regard to various exemplary components, square, module, circuit and step function to its into
General description is gone.This function is implemented as software and is also implemented as hardware depending on concrete application and application
To the design constraint of whole system.The function that those skilled in the art can realize in various ways for every kind of concrete application
Can, but this realization decision should not be interpreted as causing a departure from range disclosed by the embodiments of the present invention.
Various illustrative logical blocks, module and circuit, which can use, in conjunction with described in disclosure herein is designed to
The following component of function here is executed to realize or execute: general processor, digital signal processor (DSP), dedicated integrated electricity
It is road (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete
Any combination of hardware component or these components.General processor can be microprocessor, but alternatively, processor can
To be any conventional processors, controller, microcontroller or state machine.Processor also may be implemented as calculating the group of equipment
Close, for example, the combination of DSP and microprocessor, multi-microprocessor, one or more microprocessors combination DSP and/or it is any its
Its this configuration.
The step of method in conjunction with described in disclosure herein or algorithm, can be directly contained in hardware, be held by processor
In capable software module or in combination of the two.Software module may reside within RAM memory, flash memory, ROM storage
Device, eprom memory, eeprom memory, register, hard disk, removable disk, CD-ROM or known in the art it is any its
In the storage medium of its form.Illustrative storage medium is coupled to processor, enables a processor to from the storage medium
Information is written to the storage medium in middle reading information.In an alternative, storage medium can be integral to the processor
Together.Pocessor and storage media may reside in ASIC.ASIC may reside in user terminal.In an alternative
In, it is resident in the user terminal that pocessor and storage media can be used as discrete assembly.
In one or more exemplary designs, function can be realized in hardware, software, firmware or any combination thereof.
If realized in software, can using function as one or more instruction or code may be stored on the computer-readable medium or
It is transmitted by computer-readable medium.Computer-readable medium includes computer storage media and communication media, which is situated between
Matter includes any medium for helping for computer program to be transmitted to another position from a position.Storage medium can be energy
Any usable medium being enough accessed by a general purpose or special purpose computer.As an example and not restrictive, the computer-readable medium
It may include that RAM, ROM, EEPROM, CD-ROM or other optical disc memory apparatus, disk storage equipment or other magnetic storages are set
It is standby, or can be used for carrying or storage form be instruct or the required program code of data structure and can by general or
Special purpose computer or any other medium of general or specialized processor access.In addition, any connection can suitably claim
For computer-readable medium.For example, if using coaxial cable, optical fiber cable, twisted pair, digital subscriber line (DSL) or all
It is if the wireless technology of infrared ray, radio and microwave to send software from website, server or other remote sources, then above-mentioned coaxial
Cable, fiber optic cable, twisted pair, DSL or such as wireless technology of infrared ray, radio and microwave are included in determining for medium
Justice.As used herein, disk and CD include compact disk (CD), it is laser disk, CD, digital versatile disc (DVD), soft
Disk, Blu-ray disc, wherein disk usually magnetically reproduce data, and CD using laser optics reproduce data.Above content
Combination should also be as being included in the range of computer-readable medium.
It is exemplary embodiment disclosed by the invention above, it should be noted that in the sheet limited without departing substantially from claim
Under the premise of inventive embodiments scope of disclosure, it may be many modifications and modify.According to open embodiment described herein
The function of claim to a method, step and/or movement be not required to the execution of any particular order.In addition, although the present invention is implemented
Element disclosed in example can be described or be required in the form of individual, but be unless explicitly limited odd number, it is understood that be multiple.
It should be understood that it is used in the present context, unless the context clearly supports exceptions, singular " one
It is a " it is intended to also include plural form.It is to be further understood that "and/or" used herein refers to including one or one
Any and all possible combinations of a above project listed in association.
It is for illustration only that the embodiments of the present invention disclose embodiment sequence number, does not represent the advantages or disadvantages of the embodiments.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
Complete, relevant hardware can also be instructed to complete by program, program can store in a kind of computer-readable storage
In medium, storage medium mentioned above can be read-only memory, disk or CD etc..
It should be understood by those ordinary skilled in the art that: the discussion of any of the above embodiment is exemplary only, not
It is intended to imply that range disclosed by the embodiments of the present invention (including claim) is limited to these examples；In the think of of the embodiment of the present invention
Under road, it can also be combined between the technical characteristic in above embodiments or different embodiments, and there is this hair as above
Many other variations of the different aspect of bright embodiment, for simplicity, they are not provided in details.Therefore, all in the present invention
Within the spirit and principle of embodiment, any omission, modification, equivalent replacement, improvement for being made etc. be should be included in of the invention real
It applies within the protection scope of example.
Claims (10)
1. a kind of pick-up method of seismic first breaks point, comprising steps of
It carries out default processing respectively to multiple tracks seismic wave, is several data windows by per pass Seismic wave processing；
The first training set and the first test set are constructed using the data window of the multiple tracks seismic wave, and there are first arrivals using all
The data window of point constructs the second training set and the second test set；
Construct Classification Neural model and recurrent neural network model；
The Classification Neural model is trained and is tested using first training set and the first test set, and is utilized
Second training set and the second test set are trained and test to the recurrent neural network model；
The seismic wave to be picked up by default processing is made inferences using trained Classification Neural model, is existed
The data window of Onset point, then using trained recurrent neural network model in the data window there are Onset point
Pick up the Onset point.
2. the method as described in claim 1, which is characterized in that it is described it is default processing include:
Seismic wave is sampled, to obtain multiple sampled datas, so that it is described several using the multiple sampled data composition
A data window.
3. method according to claim 2, which is characterized in that the default processing further include: before sampling, by seismic wave
Metric amplitude data is converted to, and divided by amplitude data maximum absolute value value, to obtain amplitude data range as [- 1,1]
Seismic wave.
4. the method as described in claim 1, which is characterized in that construct the first training set using the data window of multiple tracks seismic wave
Further comprise with the first test set:
Using each data window as middle window, two adjacent data windows are respectively as upper and lower window, and common group
At a sample, the first training set and the first test set are constructed after obtaining multiple samples, wherein if the data as middle window
Only one adjacent data window of window carries out zero padding processing.
5. method as claimed in claim 4, which is characterized in that construct the first training set using the data window of multiple tracks seismic wave
Further comprise with the first test set:
It tags for first training set and first test set, the mark of first training set and first test set
It signs to whether there is Onset point as the data window of middle window, if it exists Onset point, then label is 1, and otherwise label is 0.
6. the method as described in claim 1, which is characterized in that using it is all there are the data window of Onset point building second instruction
Practice collection and the second test set further comprise:
It tags for second training set and second test set, the mark of second training set and second test set
Label are the corresponding first arrival time of the Onset point.
7. the method as described in claim 1, which is characterized in that using first training set and the first test set to described point
Connectionist model is trained and tests, and using second training set and the second test set to the recurrent nerve net
Network model is trained and test includes:
When testing trained Classification Neural model and/or recurrent neural network model, if test result is not inconsistent
Required precision is closed, then continues to be trained the Classification Neural model and/or the recurrent neural network model, until
Test result meets required precision.
8. the method as described in claim 1, which is characterized in that the method also includes steps:
More big gun single tracks pickup results are exported using visualization model, single-shot multiple tracks is picked up result, single track pickup result and prediction and missed
At least one of poor box traction substation.
9. a kind of computer equipment, comprising:
At least one processor；And
Memory, the memory are stored with the computer program that can be run on the processor, which is characterized in that the place
Manage the method executed as described in claim 1-8 any one when device executes described program.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In perform claim requires method described in 1-8 any one when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910283946.6A CN109917457B (en) | 2019-04-10 | 2019-04-10 | Method and equipment for picking up initial arrival point of seismic wave |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910283946.6A CN109917457B (en) | 2019-04-10 | 2019-04-10 | Method and equipment for picking up initial arrival point of seismic wave |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109917457A true CN109917457A (en) | 2019-06-21 |
| CN109917457B CN109917457B (en) | 2020-12-04 |
Family
ID=66969343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910283946.6A Active CN109917457B (en) | 2019-04-10 | 2019-04-10 | Method and equipment for picking up initial arrival point of seismic wave |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109917457B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110988985A (en) * | 2019-12-18 | 2020-04-10 | 北京邮电大学 | Seismic signal detection method based on waveform characteristics |
| CN111626355A (en) * | 2020-05-27 | 2020-09-04 | 中油奥博(成都)科技有限公司 | Unet + + convolutional neural network-based seismic data first arrival pickup method |
| CN112230275A (en) * | 2020-09-14 | 2021-01-15 | 河南省地震局 | Seismic waveform identification method and device and electronic equipment |
| CN112464987A (en) * | 2020-10-30 | 2021-03-09 | 中国石油天然气集团有限公司 | First-arrival position prediction result evaluation method and device |
| CN112464725A (en) * | 2020-10-30 | 2021-03-09 | 中国石油天然气集团有限公司 | First arrival picking method and device based on deep learning network |
| CN112711604A (en) * | 2019-10-25 | 2021-04-27 | 中国石油天然气股份有限公司 | Geophysical prospecting training data set construction method and device |
| CN113011597A (en) * | 2021-03-12 | 2021-06-22 | 山东英信计算机技术有限公司 | Deep learning method and device for regression task |
| CN113341459A (en) * | 2021-05-12 | 2021-09-03 | 北京大学 | Earthquake positioning method and device based on machine learning and dynamics calculation fusion |
| CN114063164A (en) * | 2020-08-05 | 2022-02-18 | 中国石油天然气股份有限公司 | First-arrival wave pickup method and device based on U-net + + convolutional neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407649A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Onset time automatic picking method of microseismic signal on the basis of time-recursive neural network |
| CN106971230A (en) * | 2017-05-10 | 2017-07-21 | 中国石油大学(北京) | First break pickup method and device based on deep learning |
| CN107807387A (en) * | 2017-10-31 | 2018-03-16 | 中国科学技术大学 | Acquisition methods when seismic first break based on neutral net is walked |
| US20190011587A1 (en) * | 2015-09-04 | 2019-01-10 | Saudi Arabian Oil Company | Automatic quality control of seismic travel time |
-
2019
- 2019-04-10 CN CN201910283946.6A patent/CN109917457B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190011587A1 (en) * | 2015-09-04 | 2019-01-10 | Saudi Arabian Oil Company | Automatic quality control of seismic travel time |
| CN106407649A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Onset time automatic picking method of microseismic signal on the basis of time-recursive neural network |
| CN106971230A (en) * | 2017-05-10 | 2017-07-21 | 中国石油大学(北京) | First break pickup method and device based on deep learning |
| CN107807387A (en) * | 2017-10-31 | 2018-03-16 | 中国科学技术大学 | Acquisition methods when seismic first break based on neutral net is walked |
Non-Patent Citations (1)
| Title |
|---|
| 刘素芹: "基于应用网格环境的复杂地表波动方程基准面静校正研究", 《中国博士学位论文全文数据库 基础科学辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112711604A (en) * | 2019-10-25 | 2021-04-27 | 中国石油天然气股份有限公司 | Geophysical prospecting training data set construction method and device |
| CN112711604B (en) * | 2019-10-25 | 2023-10-31 | 中国石油天然气股份有限公司 | Geophysical prospecting training data set construction method and device |
| CN110988985B (en) * | 2019-12-18 | 2020-11-17 | 北京邮电大学 | Seismic signal detection method based on waveform characteristics |
| CN110988985A (en) * | 2019-12-18 | 2020-04-10 | 北京邮电大学 | Seismic signal detection method based on waveform characteristics |
| CN111626355A (en) * | 2020-05-27 | 2020-09-04 | 中油奥博(成都)科技有限公司 | Unet + + convolutional neural network-based seismic data first arrival pickup method |
| CN114063164A (en) * | 2020-08-05 | 2022-02-18 | 中国石油天然气股份有限公司 | First-arrival wave pickup method and device based on U-net + + convolutional neural network |
| CN112230275A (en) * | 2020-09-14 | 2021-01-15 | 河南省地震局 | Seismic waveform identification method and device and electronic equipment |
| CN112230275B (en) * | 2020-09-14 | 2024-01-26 | 河南省地震局 | Method and device for identifying seismic waveform and electronic equipment |
| CN112464725A (en) * | 2020-10-30 | 2021-03-09 | 中国石油天然气集团有限公司 | First arrival picking method and device based on deep learning network |
| CN112464987A (en) * | 2020-10-30 | 2021-03-09 | 中国石油天然气集团有限公司 | First-arrival position prediction result evaluation method and device |
| CN113011597A (en) * | 2021-03-12 | 2021-06-22 | 山东英信计算机技术有限公司 | Deep learning method and device for regression task |
| CN113011597B (en) * | 2021-03-12 | 2023-02-28 | 山东英信计算机技术有限公司 | Deep learning method and device for regression task |
| CN113341459A (en) * | 2021-05-12 | 2021-09-03 | 北京大学 | Earthquake positioning method and device based on machine learning and dynamics calculation fusion |
| CN113341459B (en) * | 2021-05-12 | 2022-04-12 | 北京大学 | Earthquake positioning method and device based on machine learning and dynamics calculation fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109917457B (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109917457A (en) | A kind of pick-up method and equipment of seismic first breaks point | |
| CN109523993A (en) | A kind of voice languages classification method merging deep neural network with GRU based on CNN | |
| Rübel et al. | TECA: A parallel toolkit for extreme climate analysis | |
| CN109871326A (en) | A kind of method and apparatus that script is recorded | |
| CN110533974A (en) | A kind of intelligent Auto-generating Test Paper method, system and computer readable storage medium | |
| CN107403398A (en) | A kind of English education internet platform and its application method | |
| CN109446107A (en) | A kind of source code detection method and device, electronic equipment | |
| CN113359212B (en) | Reservoir characteristic prediction method and model based on deep learning | |
| CN109101519B (en) | Information acquisition system and heterogeneous information fusion system | |
| CN106598834A (en) | UI (User Interface) testing method and device | |
| CN110444058A (en) | Micro- class manufacturing system and micro- teaching system | |
| CN110866564A (en) | Season classification method, system, electronic device and medium for multiple semi-supervised images | |
| CN108268468A (en) | The analysis method and system of a kind of big data | |
| CN101727441A (en) | Evaluating method and evaluating system targeting Chinese name identifying system | |
| CN109828750A (en) | Auto-configuration data buries method, apparatus, electronic equipment and storage medium a little | |
| CN107070897A (en) | Network log storage method based on many attribute Hash duplicate removals in intruding detection system | |
| CN114067829A (en) | Reactor fault diagnosis method and device, computer equipment and storage medium | |
| CN110009289A (en) | A kind of method and system for concentrating address to send part | |
| WO2021135281A1 (en) | Multi-layer feature fusion-based endpoint detection method, apparatus, device, and medium | |
| CN106503050B (en) | Method and system for recommending reading articles based on big data | |
| CN107729510A (en) | Information interacting method, information interactive terminal and storage medium | |
| CN110188954A (en) | Terrestrial reference reliability estimation method and device based on POP network | |
| CN108986786A (en) | Interactive voice equipment ranking method, system, computer equipment and storage medium | |
| CN114782983A (en) | Road scene pedestrian detection method based on improved feature pyramid and boundary loss | |
| CN115169578A (en) | AI model production method and system based on meta-space data markers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |